Unified Walking, Running, and Recovery for Humanoids via State-Dependent Adversarial Motion Priors

TL;DR

This paper introduces a unified reinforcement learning framework enabling a humanoid robot to perform walking, running, and fall recovery seamlessly without explicit mode switching, validated through real-world experiments.

Contribution

It extends Adversarial Motion Priors with a state-dependent gating mechanism for unified control of multiple locomotion modes on hardware.

Findings

Successful recovery from prone and supine falls.

Smooth transition between walking and running.

Single policy operates at 50 Hz without mode switching logic.

Abstract

We propose a unified reinforcement learning framework that enables a single policy to perform walking, running, and fall recovery on the Unitree G1 humanoid robot, validated on physical hardware without any explicit mode-switching command at deployment. The framework extends Adversarial Motion Priors (AMP) by replacing the conventional global reference distribution with a state-dependent gate that routes each training transition to one of two discriminators: a dedicated recovery discriminator and a velocity-conditioned locomotion discriminator that jointly covers walking and running. The gate is defined by a single fixed threshold on projected gravity: the recovery discriminator is activated when body tilt exceeds approximately $37^\circ$ from vertical ($|g_z+1|>0.6$); otherwise the locomotion discriminator is used, with the normalized commanded velocity serving as a condition that selects the appropriate reference trajectory between walk and run clips. Only three LAFAN1 reference clips are required to regularize the complete behavior set. At deployment, a single frozen ONNX policy executes at 50\,Hz with no runtime mode logic; hardware experiments demonstrate successful recovery from both prone and supine falls and smooth walk-to-run transitions under the same controller.